vram.run Models Hardware Providers Cloud State of Inference
API provider data is live · Hardware & cloud pricing curated 2026-02-23

opus-mt-tc-big-tr-en

by Helsinki-NLP

235M params · translation · 93 likes · 163.2k downloads

opus-mt-tc-big-tr-en is a 235M parameter model. At Q4 quantization it requires 0GB of VRAM. It runs comfortably on GeForce RTX 4090 (5590 tok/s), GeForce RTX 5090 (8384 tok/s), M4 Max 128GB (2045 tok/s).

Inference providers

Provider$/1M in$/1M outThroughput
HF Inference

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB5590 tok/scomfortable
GeForce RTX 509032GB8384 tok/scomfortable
M4 Max 128GB128GB2045 tok/scomfortable
M4 Pro 48GB48GB1022 tok/scomfortable
M4 Pro 24GB24GB1022 tok/scomfortable
A100 PCIe 80 GB80GB10243 tok/scomfortable
H100 SXM5 80 GB80GB20602 tok/scomfortable
GeForce RTX 309024GB4943 tok/scomfortable
Radeon RX 7900 XTX24GB4087 tok/scomfortable
GeForce RTX 408016GB3967 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0